English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent years, deep learning-based approaches have significantly improvedthe performance of single-channel speech enhancement. However, due to thelimitation of training data and computational complexity, real-time enhancementof full-band (48 kHz) speech signals is still very challenging. Because of thelow energy of spectral information in the high-frequency part, it is moredifficult to directly model and enhance the full-band spectrum using neuralnetworks. To solve this problem, this paper proposes a two-stage real-timespeech enhancement model with extraction-interpolation mechanism for afull-band signal. The 48 kHz full-band time-domain signal is divided into threesub-channels by extracting, and a two-stage processing scheme of `masking +compensation' is proposed to enhance the signal in the complex domain. Afterthe two-stage enhancement, the enhanced full-band speech signal is restored byinterval interpolation. In the subjective listening and word accuracy test, ourproposed model achieves superior performance and outperforms the baseline modeloverall by 0.59 MOS and 4.0% WAcc for the non-personalized speech denoisingtask.

FB-MSTCN: A Full-Band Single-Channel Speech Enhancement Method Based on Multi-Scale Temporal Convolutional Network